diff --git a/README.md b/README.md index 9b2476977ded2b2cb477fb3170b1ebe701259ed9..ede5f15a4deffb05bf50ec590bbce7535b0e4dd5 100644 --- a/README.md +++ b/README.md @@ -98,17 +98,17 @@ - [剪枝](slim/prune) - [蒸馏](slim/distillation) - [神经网络搜索](slim/nas) -- [推理部署](inference) - - [模型导出教程](docs/advanced_tutorials/inference/EXPORT_MODEL.md) - - [预测引擎Python API使用示例](docs/advanced_tutorials/inference/INFERENCE.md) - - [C++推理部署](deploy/README.md) - - [推理Benchmark](docs/advanced_tutorials/inference/BENCHMARK_INFER_cn.md) +- [推理部署](deploy) + - [模型导出教程](docs/advanced_tutorials/deploy/EXPORT_MODEL.md) + - [Python端推理部署](deploy/python) + - [C++端推理部署](deploy/cpp) + - [推理Benchmark](docs/advanced_tutorials/deploy/BENCHMARK_INFER_cn.md) ## 模型库 - [模型库](docs/MODEL_ZOO_cn.md) -- [人脸检测模型](configs/face_detection/README.md) 开源BlazeFace系列模型，Wider-Face数据集上最高精度达到91.5%，同时具备了较高的预测性能 -- [行人检测和车辆检测预训练模型](contrib/README_cn.md) 针对不同场景的检测模型 +- [人脸检测模型](docs/featured_model/FACE_DETECTION.md) 开源BlazeFace系列模型，Wider-Face数据集上最高精度达到91.5%，同时具备了较高的预测性能 +- [行人检测和车辆检测预训练模型](docs/featured_model/CONTRIB_cn.md) 针对不同场景的检测模型 - [YOLOv3增强模型](docs/featured_model/YOLOv3_ENHANCEMENT.md) 改进原始YOLOv3，精度达到43.6%，原论文精度为33.0%，同时预测速度也得到提升 - [Objects365 2019 Challenge夺冠模型](docs/featured_model/CACascadeRCNN.md) Objects365 Full Track任务中最好的单模型之一,精度达到31.7% - [Open Images V5和Objects365数据集模型](docs/featured_model/OIDV5_BASELINE_MODEL.md) diff --git a/README_en.md b/README_en.md index c2a6c259e74e4ac7c4b07b25bc186a368ef05b43..9a3d4697c43135f11dc4e1a873b28690f5c8385b 100644 --- a/README_en.md +++ b/README_en.md @@ -112,20 +112,20 @@ The following is the relationship between COCO mAP and FPS on Tesla V100 of repr - [Model pruning](slim/prune) - [Model distillation](slim/distillation) - [Neural Architecture Search](slim/nas) -- [Deployment](inference) - - [Export model for inference](docs/advanced_tutorials/inference/EXPORT_MODEL.md) - - [Model inference](docs/advanced_tutorials/inference/INFERENCE.md) - - [C++ inference](inference/README.md) +- [Deployment](deploy) + - [Export model for inference](docs/advanced_tutorials/deploy/EXPORT_MODEL.md) + - [Python inference](deploy/python) + - [C++ inference](deploy/cpp) - [Inference benchmark](docs/advanced_tutorials/inference/BENCHMARK_INFER_cn.md) ## Model Zoo - Pretrained models are available in the [PaddleDetection model zoo](docs/MODEL_ZOO.md). -- [Face detection models](configs/face_detection/README.md) BlazeFace series model with the highest precision of 91.5% on Wider-Face dataset and outstanding inference performance. -- [Pretrained models for pedestrian and vehicle detection](contrib/README.md) Models for object detection in specific scenarios. -- [YOLOv3 enhanced model](docs/YOLOv3_ENHANCEMENT.md) Compared to MAP of 33.0% in paper, enhanced YOLOv3 reaches the MAP of 43.6% and inference speed is improved as well -- [Objects365 2019 Challenge champion model](docs/CACascadeRCNN.md) One of the best single models in Objects365 Full Track of which MAP reaches 31.7%. -- [Open Images Dataset V5 and Objects365 Dataset models](docs/OIDV5_BASELINE_MODEL.md) +- [Face detection models](docs/featured_model/FACE_DETECTION_en.md) BlazeFace series model with the highest precision of 91.5% on Wider-Face dataset and outstanding inference performance. +- [Pretrained models for pedestrian and vehicle detection](docs/featured_model/CONTRIB.md) Models for object detection in specific scenarios. +- [YOLOv3 enhanced model](docs/featured_model/YOLOv3_ENHANCEMENT.md) Compared to MAP of 33.0% in paper, enhanced YOLOv3 reaches the MAP of 43.6% and inference speed is improved as well +- [Objects365 2019 Challenge champion model](docs/featured_model/CACascadeRCNN.md) One of the best single models in Objects365 Full Track of which MAP reaches 31.7%. +- [Open Images Dataset V5 and Objects365 Dataset models](docs/featured_model/OIDV5_BASELINE_MODEL.md) - [Mobile models](configs/mobile/README.md) diff --git a/docs/advanced_tutorials/inference/BENCHMARK_INFER_cn.md b/docs/advanced_tutorials/deploy/BENCHMARK_INFER_cn.md similarity index 100% rename from docs/advanced_tutorials/inference/BENCHMARK_INFER_cn.md rename to docs/advanced_tutorials/deploy/BENCHMARK_INFER_cn.md diff --git a/docs/advanced_tutorials/deploy/DEPLOY_CPP.md b/docs/advanced_tutorials/deploy/DEPLOY_CPP.md new file mode 120000 index 0000000000000000000000000000000000000000..6460b6463b8d1ce0e19fbf00bfae08463ba2d33c --- /dev/null +++ b/docs/advanced_tutorials/deploy/DEPLOY_CPP.md @@ -0,0 +1 @@ +../../../deploy/cpp/README.md \ No newline at end of file diff --git a/docs/advanced_tutorials/deploy/DEPLOY_PY.md b/docs/advanced_tutorials/deploy/DEPLOY_PY.md new file mode 120000 index 0000000000000000000000000000000000000000..042b30c53f6b385eaac16342f29d2cb1a2d2e5c8 --- /dev/null +++ b/docs/advanced_tutorials/deploy/DEPLOY_PY.md @@ -0,0 +1 @@ +../../../deploy/python/README.md \ No newline at end of file diff --git a/docs/advanced_tutorials/inference/EXPORT_MODEL.md b/docs/advanced_tutorials/deploy/EXPORT_MODEL.md similarity index 100% rename from docs/advanced_tutorials/inference/EXPORT_MODEL.md rename to docs/advanced_tutorials/deploy/EXPORT_MODEL.md diff --git a/docs/advanced_tutorials/inference/INFERENCE.md b/docs/advanced_tutorials/deploy/INFERENCE.md similarity index 100% rename from docs/advanced_tutorials/inference/INFERENCE.md rename to docs/advanced_tutorials/deploy/INFERENCE.md diff --git a/docs/advanced_tutorials/inference/docs/linux_build.md b/docs/advanced_tutorials/deploy/docs/linux_build.md similarity index 100% rename from docs/advanced_tutorials/inference/docs/linux_build.md rename to docs/advanced_tutorials/deploy/docs/linux_build.md diff --git a/docs/advanced_tutorials/inference/docs/windows_vs2015_build.md b/docs/advanced_tutorials/deploy/docs/windows_vs2015_build.md similarity index 100% rename from docs/advanced_tutorials/inference/docs/windows_vs2015_build.md rename to docs/advanced_tutorials/deploy/docs/windows_vs2015_build.md diff --git a/docs/advanced_tutorials/inference/docs/windows_vs2019_build.md b/docs/advanced_tutorials/deploy/docs/windows_vs2019_build.md similarity index 100% rename from docs/advanced_tutorials/inference/docs/windows_vs2019_build.md rename to docs/advanced_tutorials/deploy/docs/windows_vs2019_build.md diff --git a/docs/advanced_tutorials/inference/index.rst b/docs/advanced_tutorials/deploy/index.rst similarity index 80% rename from docs/advanced_tutorials/inference/index.rst rename to docs/advanced_tutorials/deploy/index.rst index dfee271c684fc8e94df887db650a479bd080eac5..a927e8b9cfd34b9443983d3af459fd03a465cfaf 100644 --- a/docs/advanced_tutorials/inference/index.rst +++ b/docs/advanced_tutorials/deploy/index.rst @@ -5,6 +5,6 @@ :maxdepth: 2 EXPORT_MODEL.md - INFERENCE.md + DEPLOY_PY.md + DEPLOY_CPP.md BENCHMARK_INFER_cn.md - DEPLOYMENT.md diff --git a/docs/advanced_tutorials/index.rst b/docs/advanced_tutorials/index.rst index eb62cf7d6141ca67a940c19fbc2422f77b4495e1..5f1f14905a9daaf0518b667abf447386741a8e04 100644 --- a/docs/advanced_tutorials/index.rst +++ b/docs/advanced_tutorials/index.rst @@ -4,9 +4,9 @@ .. toctree:: :maxdepth: 2 + deploy/index READER.md MODEL_TECHNICAL.md CONFIG_cn.md TRANSFER_LEARNING_cn.md slim/index - inference/index diff --git a/docs/advanced_tutorials/inference/DEPLOYMENT.md b/docs/advanced_tutorials/inference/DEPLOYMENT.md deleted file mode 120000 index 8ff4f4b539012e7676e70cf8316fbcbe337fb99a..0000000000000000000000000000000000000000 --- a/docs/advanced_tutorials/inference/DEPLOYMENT.md +++ /dev/null @@ -1 +0,0 @@ -../../../../deploy/cpp/README.md \ No newline at end of file